Learning Sunspot Classification

• Autorzy: Nguyen T.T. , Willis C.P. , Paddon D.J. , Nguyen S.H. , Nguyen H.S.
• Języki publikacji: EN

Abstrakty

EN

Sunspots are the subject of interest to many astronomers and solar physicists. Sunspot observation, analysis and classification form an important part of furthering the knowledge about the Sun. Sunspot classification is a manual and very labor intensive process that could be automated if successfully learned by a machine. This paper presents machine learning approaches to the problem of sunspot classification. The classification scheme attempted was the seven-class Modified Zurich scheme [18]. The data was obtained by processing NASA SOHO/MDI satellite images to extract individual sunspots and their attributes. A series of experiments were performed on the training dataset with an aim of learning sunspot classification and improving prediction accuracy. The experiments involved using decision trees, rough sets, hierarchical clustering and layered learning methods. Sunspots were characterized by their visual properties like size, shape, positions, and were manually classified by comparing extracted sunspots with corresponding active region maps (ARMaps) from the Mees Observatory at the Institute for Astronomy, University of Hawaii.

Słowa kluczowe

EN

sunspot classification; layered learning; rough sets; machine learning

• Wydawca: IOS Press
• Czasopismo: Fundamenta Informaticae
• Rocznik: 2006
• Tom: Vol. 72, nr 1-3
• Strony: 295--309
• Opis fizyczny: rys., tab., wykr., bibliogr. 22 poz.

Twórcy

autor

Nguyen T.T.

autor

Willis C.P.

autor

Paddon D.J.

autor

Nguyen S.H.

autor

Nguyen H.S.

• Department of Computer Science, University of Bath Bath BA2 7AY, United Kingdom

Bibliografia

• [1] Sinh Hoa Nguyen, Trung Thanh Nguyen, Hung Son Nguyen Rough Set Approach to Sunspot Classification Problem In Dominik Slezak, Jingtao Yao, James F. Peters, Wojciech Ziarko, Xiaohua Hu (Eds.): Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing, 10th International Conference, RSFDGrC 2005, Regina, Canada, August 31 - September 3, 2005, Proceedings, Part II. Lecture Notes in Computer Science 3642 Springer 2005. pages 263-272
• [2] Trung Thanh Nguyen, Claire P. Willis, Derek J. Paddon, Sinh Hoa Nguyen, and Hung Son Nguyen. Data Mining Approach to Sunspot Classification Problem in Rough Set Techniques in Knowledge Discovery Workshop at The 9th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD-05) in Hanoi, Vietnam 18-20 May 2005.
• [3] Bazan J., Szczuka M. RSES and RSESlib - A Collection of Tools for Rough Set Computations, Proc. Of RSCTC'2000, LNAI 2005, Springer Verlag, Berlin, 2001
• [4] P. Stone. Layered Learning in Multi-Agent Systems: A Winning Approach to Robotic Soccer. The MIT Press, Cambridge,MA, 2000.
• [5] P. H. Scherrer, et al., Sol. Phys., 162, 129, 1995.
• [6] Trung Thanh Nguyen, Claire P. Willis, Derek J. Paddon, and Hung Son Nguyen. On learning of sunspot classification. In Mieczyslaw A. Klopotek, Slawomir T. Wierzchon, and Krzysztof Trojanowski, editors, Intelligent Information Systems, Proceedings of IIPWM'04, May 17-20, 2004, Zakopane, Poland, Advances in Soft Computing, pages 59-68. Springer, 2004.
• [7] Sinh Hoa Nguyen, Jan Bazan, Andrzej Skowron, and Hung Son Nguyen. Layered learning for concept synthesis. In Jim F. Peters, Andrzej Skowron, JerzyW. Grzymala-Busse, Bozena Kostek, RomanW. Swiniarski, and Marcin S. Szczuka, editors, Transactions on Rough Sets I, volume LNCS 3100 of Lecture Notes on Computer Science, pages 187-208. Springer, 2004.
• [8] Sinh Hoa Nguyen and Hung Son Nguyen. Rough set approach to approximation of concepts fromtaxonomy. In Proceedings of Knowledge Discovery and Ontologies Workshop (KDO-04) at ECML/PKDD 2004, September 24, 2004, Pisa, Italy, 2004.
• [9] Sinh Hoa Nguyen and Hung Son Nguyen. Learning concept approximation from uncertain decision tables. In Monitoring, Security, and Rescue Techniques in Multiagent Systems Dunin-Keplicz, B.; Jankowski, A.; Skowron, A.; Szczuka, M. (Eds.), Advances in Soft Computing, Springer-Verlag 2005, page 249-260.
• [10] Freund, Y., and R. E. Schapire Experiments with a new boosting algorithm. Proc. Thirteenth International Conference on Machine Learning,Morgan Kaufmann, 1996, pages 148-156.
• [11] R. J. Bray and R. E. Loughhead. Sunspots. Dover Publications, New York, 1964.
• [12] P. Hadjinian R. Stadler J. Verhees Cabena, P. and A. Zanasi. Discovering data mining: From concept to implementation. Prentice Hall, Upper Saddle River, NJ., 1998.
• [13] G. Gora and A. Wojna., RIONA: A New Classification System Combining Rule Induction and Instance-Based Learning, Fundamenta Informaticae, 51(4), 2002, pages 369-390
• [14] Grzymała-Busse J., A New Version of the Rule Induction System LERS Fundamenta Informaticae, Vol.31(1), 1997, pp. 27-39
• [15] R. Kohavi and F. Provost. Machine learning: Special issue on application of machine learning and the knowledge discovery process. Machine Learning, 30, 1998.
• [16] P. Langley and H. A. Simon. Applications of machine learning and rule induction. Communications of the ACM, 38(11):55-64, 1995.
• [17] K. J. H. Phillips. Guide to the Sun. Cambridge University Press, 1992.
• [18] P. McIntosh, Solar Physics 125, 251, 1990.
• [19] J. R. Quinlan. Induction of decision trees. Machine Learning, 1(1):81-106, 1986.
• [20] I. H. Witten and Frank E. Data Mining: practical machine learning tools and techniques with Java implementations. Morgan Kaufmann Publishers, San Francisco, CA., 2000.
• [21] The RSES Homepage http://logic.mimuv.edu.pl/~rses.
• [22] The WEKA Homepage, http://www.cs.waikato.ac.nz.